DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Oh, Hyung-Seok, Lee, Sang-Hoon, Cho, Deok-Hyeon, Lee, Seong-Whan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915111287914496
author Oh, Hyung-Seok
Lee, Sang-Hoon
Cho, Deok-Hyeon
Lee, Seong-Whan
author_facet Oh, Hyung-Seok
Lee, Sang-Hoon
Cho, Deok-Hyeon
Lee, Seong-Whan
contents Emotional voice conversion (EVC) involves modifying various acoustic characteristics, such as pitch and spectral envelope, to match a desired emotional state while preserving the speaker's identity. Existing EVC methods often rely on text transcriptions or time-alignment information and struggle to handle varying speech durations effectively. In this paper, we propose DurFlex-EVC, a duration-flexible EVC framework that operates without the need for text or alignment information. We introduce a unit aligner that models contextual information by aligning speech with discrete units representing content, eliminating the need for text or speech-text alignment. Additionally, we design a style autoencoder that effectively disentangles content and emotional style, allowing precise manipulation of the emotional characteristics of the speech. We further enhance emotional expressiveness through a hierarchical stylize encoder that applies the target emotional style at multiple hierarchical levels, refining the stylization process to improve the naturalness and expressiveness of the converted speech. Experimental results from subjective and objective evaluations demonstrate that our approach outperforms baseline models, effectively handling duration variability and enhancing emotional expressiveness in the converted speech.
format Preprint
id arxiv_https___arxiv_org_abs_2401_08095
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignment
Oh, Hyung-Seok
Lee, Sang-Hoon
Cho, Deok-Hyeon
Lee, Seong-Whan
Sound
Artificial Intelligence
Audio and Speech Processing
Emotional voice conversion (EVC) involves modifying various acoustic characteristics, such as pitch and spectral envelope, to match a desired emotional state while preserving the speaker's identity. Existing EVC methods often rely on text transcriptions or time-alignment information and struggle to handle varying speech durations effectively. In this paper, we propose DurFlex-EVC, a duration-flexible EVC framework that operates without the need for text or alignment information. We introduce a unit aligner that models contextual information by aligning speech with discrete units representing content, eliminating the need for text or speech-text alignment. Additionally, we design a style autoencoder that effectively disentangles content and emotional style, allowing precise manipulation of the emotional characteristics of the speech. We further enhance emotional expressiveness through a hierarchical stylize encoder that applies the target emotional style at multiple hierarchical levels, refining the stylization process to improve the naturalness and expressiveness of the converted speech. Experimental results from subjective and objective evaluations demonstrate that our approach outperforms baseline models, effectively handling duration variability and enhancing emotional expressiveness in the converted speech.
title DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations without Text Alignment
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2401.08095